Pranav Gupta

Why it mattered. Leaders needed faster, more reliable answers that combined governed KPIs, weekly pacing drivers, and unstructured business context — without waiting for ad-hoc analyst pulls or piecing together fragmented sales, attendance, and pacing reports.

What I built. As part of the Neural Nets team, I helped design and productionize an enterprise intelligence layer for Brooklyn Nets ticketing — a live, governed decision-support system on ChatGPT Actions, AWS (API Gateway, ALB, EC2), FastAPI, and Snowflake, with Snowflake Cortex Search powering semantic retrieval and AI document parsing handling unstructured PDFs. My work spanned architecture, data modeling, API evolution, and production stabilization: I expanded the structured semantic foundation, evolved the API from fixed metrics to validated dynamic metrics, and stabilized the live backend through query, deployment, and warehouse fixes.

How leaders use it. Executives get grounded, source-aware answers in natural language — blending structured KPIs with weekly pacing drivers and qualitative business context. The assistant materially compressed time-to-insight: club forecasting moved from over an hour to roughly five minutes, and ad hoc historical analysis dropped from four-to-five hours to under thirty minutes, on a unified semantic layer covering five years of ticketing data.

Why it mattered. Raw revenue isn't a fair way to compare sales reps. Reps carry different goals, roles, tenures, and opportunity sets — leaders needed a goal-relative, defensible way to rank performance and surface coaching opportunities.

What I built. A standardized, goal-relative performance scoring model that lets leaders compare reps fairly across departments and years. Refined across four iterations on direct leader feedback, with annual and quarterly views and percentile-based pattern overlays.

How leaders use it. Anchors coaching, recognition, performance reviews, and goal-calibration conversations — and surfaces in-year trajectory changes an annual score would smooth over.

Why it mattered. Sales reps and leaders needed faster visibility into pacing, inventory, trends, and gap-to-goal opportunities to make better in-cycle selling decisions.

What I built. Piloted dashboards giving reps and managers clear views into sales performance, inventory, pacing, and opportunity gaps.

How leaders use it. Strengthened a more data-driven selling culture across the team, improved opportunity identification, and reduced reliance on ad-hoc pulls during pacing conversations.

Why it mattered. Broker activity inside the season ticket member base undermined pricing integrity, diluted STM value, conditioned demand to wait for cheaper secondary-market inventory, and weakened fan-first access — creating margin leakage on one franchise and missed upside on another. Leaders needed a structured, evidence-based way to distinguish broker behavior from legitimate fan use.

What I built. Led the end-to-end development of BKSE's first broker identification methodology — a seat-, event-, and account-level framework that combined ticketing lifecycle, resale, transfer, attendance, and account-tenure signals into confidence-graded broker buckets. The work moved through three phases: defining the business problem and indicators, refining the population through manual validation and confidence scoring, and translating findings into section- and price-point-specific business actions.

How leaders use it. Anchors targeted account-level decisions, supports pricing and inventory strategy, and gives sales and service teams a defensible framework rather than anecdotal flags. The methodology was presented to senior leadership and later shared with 300+ sports industry professionals on the Russell-Scibiti call as a best-practice example of analytics-driven ticketing policy.

Why it mattered. Leaders across multiple departments needed a more rigorous, data-driven way to evaluate staffing levels, sales productivity, and resource allocation.

What I built. A multi-iteration predictive staffing and rep ROI model spanning multiple departments, refined with leader input across versions.

How leaders use it. Supports staffing decisions with consistent, comparable evidence; helps leaders right-size teams and make resource allocation choices with greater confidence.

Why it mattered. The business needed sharper customer segmentation to support targeted marketing and retention strategies.

What I built. A customer retention model in Python that segments the base and supports personalized marketing and retention campaigns.

How leaders use it. Powers more targeted retention initiatives and personalized offers, with segmentation logic transparent enough for marketing leaders to use directly.